To refer to this page use:
|Abstract:||© 2014 A. Agarwal, A. Badanidiyuru, M. Dudík, R.E. Schapire & A. Slivkins. We study decision making when each action is described by a set of objectives, all of which are to be maximized. During the training phase, we have access to the actions of an outside agent ("mentor"). In the test phase, our goal is to maximally improve upon the mentor's (unobserved) actions across all objectives. We present an algorithm with a vanishing regret compared with the optimal possible improvement, and show that our regret bound is the best possible. The bound is independent of the number of actions, and scales only as the logarithm of the number of objectives.|
|Citation:||Agarwal, A, Badanidiyuru, A, Dudík, M, Schapire, RE, Slivkins, A. (2014). Robust multi-objective learning with mentor feedback. Journal of Machine Learning Research, 35 (726 - 741|
|Pages:||726 - 741|
|Type of Material:||Conference Article|
|Journal/Proceeding Title:||Journal of Machine Learning Research|
|Version:||Final published version. This is an open access article.|
Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.